Scribd
Upload
214 views14 pages

Final Year Project

Uploaded by

ommishraf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
214 views14 pages

Final Year Project

Uploaded by

ommishraf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

Aavishkar

Inter-Collegiate Aavishkar Research Convention 2023-24


Category : 5 Level : UG

Brain Tumor Detection


Using CNN

Slot No :
Introduction
● In recent years, AI/ML has gained significant prominence in healthcare, offering innovative
solutions.

● From early disease detection to personalized treatment, AI/ML is transforming medical


practices.

● Today, we focus on one such application: using deep learning to detect brain tumors and
Knowing the role of AI/ML in modern medicine

● The project involves the development of sophisticated computer algorithms that can
analyze medical images, such as MRI scans, to automatically identify the presence and
characteristics of brain tumors.

● This technology has the potential to revolutionize the way we diagnose and treat brain
tumors, offering faster and more accurate results, which are critical in improving patient
outcomes and saving lives
Literature review
• In recent years, there has been a growing body of research and studies in the field of
brain tumor detection using deep learning techniques.

• Some key findings and trends from this research include:


a. Increased Accuracy
b. Early Detection
c. Segmentation
d. Integration with Clinical Workflow
e. Transfer Learning
f. Data Challenges
g. Ethical Considerations
h. Clinical Validation
Need Significance
• High Disease Prevalence: Brain tumors are a • Improving Diagnosis: The project work aims to
significant health concern globally, with a high significantly improve the accuracy and speed of
prevalence rate. Early and accurate detection is brain tumor detection.
crucial for timely treatment and better patient
outcomes. • Enhancing Patient Outcomes: Timely detection of
brain tumors can result in more successful
treatment outcomes and a higher quality of life for
• Challenges in Diagnosis: Traditional methods of brain patients.
tumor diagnosis, while effective, can be time-
consuming and prone to human error. There is a need • Reducing Healthcare Costs: By streamlining the
for more efficient and reliable diagnostic tools. diagnostic process and reducing the need for
extensive manual analysis, your work can help
lower healthcare costs.

• AI/ML in Healthcare: The project highlights the


growing role of AI/ML in healthcare, showcasing
how technology can assist medical professionals
in making critical decisions.
Deep Learning Framework
● TensorFlow: TensorFlow is a popular open-source deep learning framework
developed by Google. It is scalability and wide adoption in both research and industry.

● Keras: Keras is a high-level neural networks API written in Python. its simplicity and
user-friendliness make it a popular choice for deep learning projects.

● Combining both utilized Keras as a user-friendly, high-level API for developing neural
networks, and it ran on top of the TensorFlow backend.

● This combination allowed us to harness the best of both worlds: Keras for its simplicity
and TensorFlow for its power and scalability.

● Keras with TensorFlow is compatible with various hardware accelerators, such as


GPUs, which can significantly speed up deep learning tasks.
Hardware and Software

• Hardware :
1. Laptop/PC
2. GPU ( Alternative cloud computing )

• Software :
1. Python
2. Tensorflow
3. Keras
4. matplotlib
5. Google colab
6. Jupyter Notebook
Methodology
● Step 1: Importing Libraries

● Step 2: Setting up the dataset path and directories

● Step 3: Image preprocessing

● Step 4: Setting up image size (150x150), batch size, and epochs

● Step 5: Building the model architecture

● Step 6: Training the model

● Step 7: Visualization and Evaluation


Accuracy
Model Name Accuracy

AlexNet 88%

LeNet 95%

VGG-19 84%

InceptionNet V3 96%

ResNet 63%
InceptionNet-V3 Architecture

Reference : Advanced Guide to Inception v3 | Cloud


TPU | Google Cloud
Results
Results

Formula :
Precision = True Positives / (True Positives + False Positives)
Recall = True Positives / (True Positives + False Negatives)
F1 Score = 2 * (Precision * Recall) / (Precision + Recall)
Key findings
● Enhanced Detection Accuracy: using the project, we have demonstrated that the
application of deep learning techniques, particularly utilizing InceptionNet and Keras,
can significantly enhance the accuracy of brain tumor detection in medical images.

● Timely Detection: As seen that the model has the potential to detect brain tumors at
early stages, which is pivotal for timely medical interventions and improved patient
outcomes.

● Balanced Precision and Recall: The model strikes a balance between precision and
recall, minimizing both false positives and false negatives, making it suitable for real-
world clinical use.

● Clinical Applicability: We've underscored the clinical applicability of our work, as it


can serve as a valuable decision support tool for medical professionals, aiding in
diagnosis and treatment planning.
References
[1] W. Yu, K. Yang, Y. Bai, T. Xiao, H. Yao, and Y. Rui, “Visualizing and Comparing AlexNet and VGG using Deconvolutional Layers”.

[2]A. Garg and V. Mago, “Role of machine learning in medical research: A survey,” Comput. Sci. Rev., vol. 40, p. 100370, May 2021, doi:
10.1016/j.cosrev.2021.100370.

[3]J. Gu et al., “Recent advances in convolutional neural networks,” Pattern Recognit., vol. 77, pp. 354–377, May 2018, doi:
10.1016/j.patcog.2017.10.013.

[4]D. Ravi et al., “Deep Learning for Health Informatics,” IEEE J. Biomed. Health Inform., vol. 21, no. 1, pp. 4–21, Jan. 2017, doi:
10.1109/JBHI.2016.2636665.

[5]S. Pereira, A. Pinto, V. Alves, and C. A. Silva, “Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images,” IEEE
Trans. Med. Imaging, vol. 35, no. 5, pp. 1240–1251, May 2016, doi: 10.1109/TMI.2016.2538465.

[6]I. Wahlang et al., “Brain Magnetic Resonance Imaging Classification Using Deep Learning Architectures with Gender and Age,” Sensors,
vol. 22, no. 5, p. 1766, Feb. 2022, doi: 10.3390/s22051766.

[7]Turk, Omer, D. Ozhan, E. Acar, T. C. Akinci, and M. Yilmaz, “Automatic detection of brain tumors with the aid of ensemble deep learning
architectures and class activation map indicators by employing magnetic resonance images,” Z. Für Med. Phys., p. S0939388922001313, Dec.
2022, doi: 10.1016/j.zemedi.2022.11.010.

[8]M. Shin, M. Kim, and D.-S. Kwon, “Baseline CNN structure analysis for facial expression recognition,” in 2016 25th IEEE International
Symposium on Robot and Human Interactive Communication (RO-MAN), New York, NY, USA: IEEE, Aug. 2016, pp. 724–729. doi:
10.1109/ROMAN.2016.7745199.
Thankyou

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy